percpu: fix this_cpu_sub() subtrahend casting for unsigneds

this_cpu_sub() is implemented as negation and addition.

This patch casts the adjustment to the counter type before negation to
sign extend the adjustment.  This helps in cases where the counter type
is wider than an unsigned adjustment.  An alternative to this patch is
to declare such operations unsupported, but it seemed useful to avoid
surprises.

This patch specifically helps the following example:
  unsigned int delta = 1
  preempt_disable()
  this_cpu_write(long_counter, 0)
  this_cpu_sub(long_counter, delta)
  preempt_enable()

Before this change long_counter on a 64 bit machine ends with value
0xffffffff, rather than 0xffffffffffffffff.  This is because
this_cpu_sub(pcp, delta) boils down to this_cpu_add(pcp, -delta),
which is basically:
  long_counter = 0 + 0xffffffff

Also apply the same cast to:
  __this_cpu_sub()
  __this_cpu_sub_return()
  this_cpu_sub_return()

All percpu_test.ko passes, especially the following cases which
previously failed:

  l -= ui_one;
  __this_cpu_sub(long_counter, ui_one);
  CHECK(l, long_counter, -1);

  l -= ui_one;
  this_cpu_sub(long_counter, ui_one);
  CHECK(l, long_counter, -1);
  CHECK(l, long_counter, 0xffffffffffffffff);

  ul -= ui_one;
  __this_cpu_sub(ulong_counter, ui_one);
  CHECK(ul, ulong_counter, -1);
  CHECK(ul, ulong_counter, 0xffffffffffffffff);

  ul = this_cpu_sub_return(ulong_counter, ui_one);
  CHECK(ul, ulong_counter, 2);

  ul = __this_cpu_sub_return(ulong_counter, ui_one);
  CHECK(ul, ulong_counter, 1);

Signed-off-by: Greg Thelen <gthelen@google.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

arch/x86/include/asm/percpu.h

@@ -128,7 +128,8 @@ do {							\
 do {									\
 	typedef typeof(var) pao_T__;					\
 	const int pao_ID__ = (__builtin_constant_p(val) &&		\
-			      ((val) == 1 || (val) == -1)) ? (val) : 0;	\
+			      ((val) == 1 || (val) == -1)) ?		\
+				(int)(val) : 0;				\
 	if (0) {							\
 		pao_T__ pao_tmp__;					\
 		pao_tmp__ = (val);					\

include/linux/percpu.h

@@ -332,7 +332,7 @@ do {									\
 #endif
 
 #ifndef this_cpu_sub
-# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(val))
+# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(typeof(pcp))(val))
 #endif
 
 #ifndef this_cpu_inc
@@ -418,7 +418,7 @@ do {									\
 # define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
 #endif
 
-#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(val))
+#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(typeof(pcp))(val))
 #define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
 #define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
 
@@ -586,7 +586,7 @@ do {									\
 #endif
 
 #ifndef __this_cpu_sub
-# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(val))
+# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(typeof(pcp))(val))
 #endif
 
 #ifndef __this_cpu_inc
@@ -668,7 +668,7 @@ do {									\
 	__pcpu_size_call_return2(__this_cpu_add_return_, pcp, val)
 #endif
 
-#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(val))
+#define __this_cpu_sub_return(pcp, val)	__this_cpu_add_return(pcp, -(typeof(pcp))(val))
 #define __this_cpu_inc_return(pcp)	__this_cpu_add_return(pcp, 1)
 #define __this_cpu_dec_return(pcp)	__this_cpu_add_return(pcp, -1)